Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    organizations and locations related to political and economic events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to specific companies and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.04
    2:0.24
    3:0.06
    4:0.17
    5:0.05
    6:0.04
    7:0.03
    8:0.05
    9:0.11
    10:0.07
    11:0.04
    Negative Logits
     juven
    -1.39
     scrut
    -1.37
    ascript
    -1.34
    regn
    -1.32
     occas
    -1.32
     rele
    -1.30
    ��
    -1.29
    iqueness
    -1.27
     adolesc
    -1.22
    atural
    -1.22
    POSITIVE LOGITS
     Ltd
    1.42
     Federation
    1.33
    utan
    1.32
    adesh
    1.27
    apons
    1.25
     Holdings
    1.25
    USD
    1.23
     Ton
    1.23
     Organisation
    1.21
     Province
    1.20
    Act Density 0.002%

    No Known Activations